CN102741849B - Cause in misdiagnosis pick-up unit and cause in misdiagnosis detection method - Google Patents
Cause in misdiagnosis pick-up unit and cause in misdiagnosis detection method Download PDFInfo
- Publication number
- CN102741849B CN102741849B CN201180007768.6A CN201180007768A CN102741849B CN 102741849 B CN102741849 B CN 102741849B CN 201180007768 A CN201180007768 A CN 201180007768A CN 102741849 B CN102741849 B CN 102741849B
- Authority
- CN
- China
- Prior art keywords
- read tablet
- result
- read
- image
- guidance content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims description 10
- 238000003745 diagnosis Methods 0.000 claims description 135
- 238000002405 diagnostic procedure Methods 0.000 claims description 86
- 238000000034 method Methods 0.000 claims description 81
- 230000008569 process Effects 0.000 claims description 68
- 238000000605 extraction Methods 0.000 claims description 26
- 239000000284 extract Substances 0.000 claims description 10
- 238000002059 diagnostic imaging Methods 0.000 claims description 6
- 206010028980 Neoplasm Diseases 0.000 description 19
- 201000011510 cancer Diseases 0.000 description 16
- 238000004590 computer program Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000007170 pathology Effects 0.000 description 9
- 230000015572 biosynthetic process Effects 0.000 description 5
- 238000002604 ultrasonography Methods 0.000 description 4
- 208000009956 adenocarcinoma Diseases 0.000 description 3
- 210000000481 breast Anatomy 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 3
- 210000005075 mammary gland Anatomy 0.000 description 3
- 201000007423 tubular adenocarcinoma Diseases 0.000 description 3
- 208000006402 Ductal Carcinoma Diseases 0.000 description 2
- 238000001574 biopsy Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 238000004195 computer-aided diagnosis Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000002592 echocardiography Methods 0.000 description 2
- 230000008595 infiltration Effects 0.000 description 2
- 238000001764 infiltration Methods 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 208000030270 breast disease Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 201000010879 mucinous adenocarcinoma Diseases 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
- A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Business, Economics & Management (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biomedical Technology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
Read tablet educational devices (100) comprising: read tablet picture cues portion (102), by object read tablet picture cues to read tablet person; Read tablet result obtaining portion (103), obtains the first read tablet result and read tablet time, and this first read tablet result is the read tablet result of read tablet person for object read tablet image, and this read tablet time is the read tablet that read tablet person carries out object read tablet image is the time used; Read tablet result judging part (104), by comparing with the first read tablet result obtained in read tablet result obtaining portion (103) the determination diagnostic result for object read tablet image, judges correcting errors of the first read tablet result; And guidance content Attributions selection portion (105), when judging the first read tablet result as mistake, according to the read tablet time, select the attribute of the guidance content to read tablet person's prompting.
Description
Technical field
The present invention relates to cause in misdiagnosis pick-up unit and cause in misdiagnosis detection method.
Background technology
Due to the deficiency of chronic read tablet doctor, the mistaken diagnosis of the doctor of read tablet lack of experience becomes a larger problem.Bringing greater impact in mistaken diagnosis the prognosis of patient is " mistake of existence diagnosis " and " mistake of character diagnosis ".The mistake of existence diagnosis refers to and have ignored pathology.The diagnostic error of Quality refers to, mistake appears in the diagnosis of the pathology detected.
In order to prevent such mistaken diagnosis, take the measure of various reply mistake.For " mistake of existence diagnosis ", have employed the detection support method utilizing and undertaken by the CAD (ComputerAidedDiagnosis: computer-aided diagnosis) etc. of computer auto-detection lesion region.Accordingly, can improve and prevent the uncared-for effect of pathology.
In addition, for " mistake of character diagnosis ", Prevent countermeasures is taked by carrying out read tablet education by veteran doctor.Veteran doctor, when educating new doctor, except carrying out the positive erroneous judgement diagnosed, also carries out detailed guidance according to the cause in misdiagnosis of new doctor.Such as, when mistake appears in the judgement of " A cancer ", when there is mistake in the diagnostic process in order to judge A cancer, then this diagnostic process is instructed.In addition, mistaken diagnosis appears in the identification of the image model corresponding with the diagnostic process of A cancer, image model is instructed.
For above-mentioned Problems of Misdiagnosis, propose the method (for example, referring to patent documentation 1) extracting mistaken diagnosis from read tablet time of doctor (read tablet person) (wanting the time during read tablet).In the record method of patent documentation 1, from before read tablet database calculate the standard read tablet time, when the read tablet time is above standard the read tablet time, be judged as the possibility of mistaken diagnosis.Accordingly, the judgement of mistaken diagnosis immediately can be carried out for the case of a part.
(prior art document)
(patent documentation)
Patent documentation 1 Japanese Unexamined Patent Publication No. 2009-82182 public Reported
But, in the device described in patent documentation 1, there is the problem that can not detect the reason of mistaken diagnosis.
The reason of mistaken diagnosis roughly can consider two.First reason is, mistake has appearred in the corresponding relation of case and diagnostic process.Second reason is, mistake has appearred in the corresponding relation of case and image model.
Cause in misdiagnosis can be divided into the above-mentioned reason of two kinds to be that read tablet person is divided into the cause in two stages in the process of study negatoscopy.
In the initial period of learning process, read tablet person learns the diagnostic process of each case, and diagnoses according to diagnostic process.In this one-phase, the checkup item comprised in diagnostic process is confirmed seriatim, while diagnose.In the next stage, read tablet person correspondingly to remember direct to each case and image model together, thus is contrasted by the pattern of image and diagnose.That is, the mistaken diagnosis produced read tablet person is, in certain above-mentioned learning process, produces when obtaining the knowledge of mistake.
Therefore, when occurring mistaken diagnosis, needing judgement to be " mistake of the corresponding relation of case and diagnostic process " or " mistake of the corresponding relation of case and image model ", and being prompted to read tablet person.
Summary of the invention
Therefore, the present invention is in order to solve the above problems, and object is to provide a kind of when read tablet person's mistaken diagnosis, for detecting the device of cause in misdiagnosis and the method for detecting cause in misdiagnosis.
The present invention is in order to solve above-mentioned problem, cause in misdiagnosis pick-up unit involved by certain situation, comprise: read tablet picture cues portion, using during read tablet is reported as being used for the object read tablet picture cues of read tablet image of diagnostic imaging to read tablet person, described read tablet report is described read tablet image and the combination for the determination diagnostic result of described read tablet image, read tablet result obtaining portion, obtain the first read tablet result and read tablet time, described first read tablet is as a result, described read tablet person is for the read tablet result of described object read tablet image, the described read tablet time is, the time used when described read tablet person carries out read tablet for described object read tablet image, read tablet result judging part, by for described object read tablet image determination diagnostic result, compare with the described first read tablet result to be obtained by described read tablet result obtaining portion, judge correcting errors of described first read tablet result, and guidance content Attributions selection portion, when described first read tablet result is judged as mistake by described read tablet result judging part, perform at least one party that (a) first selects process and (b) second to select in process, described first selects process to refer to, when the described read tablet time obtained by described read tablet result obtaining portion is larger than threshold value, select the attribute being used to guide the guidance content of the diagnostic process of the case of the case name shown in described first read tablet result, using the attribute as the guidance content to described read tablet person's prompting, described second selects process to refer to, when the described read tablet time is below described threshold value, select the attribute being used to guide the guidance content of the image model of the case of the case name shown in described first read tablet result, using the attribute as the described guidance content to described read tablet person's prompting.
Above-mentioned cause in misdiagnosis can utilize the read tablet time to classify.When there occurs " mistake of the corresponding relation of case and diagnostic process ", because read tablet person confirms to diagnose to diagnostic process one by one, therefore feature increases the read tablet time.In addition, when there occurs " mistake of the corresponding relation of case and image model ", can consider that read tablet person has finished the study of diagnostic process, knowing diagnostic process.Therefore, read tablet person, without the need to confirming diagnostic process, mainly just can diagnose from image model, so the read tablet time shortens.Therefore, when the read tablet time is long, be judged as YES the mistaken diagnosis occurred because of " mistake of the corresponding relation of case and diagnostic process ", when the read tablet time is short, be judged as YES the mistaken diagnosis occurred because of " mistake of the corresponding relation of case and image model ".
Like this, which and the mistaken diagnosis that occurs that can judge because of diagnostic process and image model according to the read tablet time, therefore, it is possible to automatically select the attribute of the guidance content corresponding with cause in misdiagnosis.Further, can, according to the attribute of the guidance content selected, read tablet person be selected can to correct the guidance content of cause in misdiagnosis rightly.Further, the retrieval time of read tablet person to the guidance content of mistaken diagnosis time institute reference can be reduced, therefore, it is possible to shorten the learning time of read tablet person.
And, the present invention can not only as have this feature the cause in misdiagnosis pick-up unit of handling part realize, and can to realize as using the cause in misdiagnosis detection method of the process performed by the distinctive handling part comprised in cause in misdiagnosis pick-up unit as step.Further, the program that computing machine can be made as the distinctive handling part possessed for cause in misdiagnosis pick-up unit to play function realizes.Further, can realize as the program making computing machine perform the distinctive step comprised in cause in misdiagnosis detection method.Further, these programs are that the communication network such as nonvolatile recording medium or the Internet that can be able to be read by computing machines such as CD-ROM (CompactDisc-ReadOnlyMemory) is circulated.
By the present invention, read tablet person, when mistaken diagnosis, can detect cause in misdiagnosis.
Accompanying drawing explanation
Fig. 1 is that the characteristic function of tool of the read tablet educational devices illustrated involved by the embodiment of the present invention 1 forms block scheme.
Fig. 2 A is the figure that the ultrasonography example as read tablet image stored in read tablet report database is shown.
Fig. 2 B is the figure of the example that the read tablet information stored in read tablet report database is shown.
Fig. 3 is the figure of an example of the image illustrated suggested by read tablet picture cues portion.
Fig. 4 is the figure of the example that representative image and read tablet flow process are shown.
Fig. 5 shows a histogrammic example of read tablet time.
Fig. 6 shows an example of guidance content database.
Fig. 7 is the process flow diagram of the whole treatment schemees illustrated performed by the read tablet educational devices involved by embodiments of the invention 1.
Fig. 8 is the process flow diagram of the detailed process that the guidance content Attributions selection process (the step S105 of Fig. 7) carried out in guidance content Attributions selection portion is shown.
Fig. 9 shows an example of the picture that efferent exports to output medium.
Figure 10 shows an example of the picture that efferent exports to output medium.
Figure 11 is the block scheme that the characteristic function of tool of the read tablet educational devices illustrated involved by the embodiment of the present invention 2 is formed.
Figure 12 A shows an example of the mistaken diagnosis position on read tablet image.
Figure 12 B shows an example of the mistaken diagnosis position on diagnostic process.
Figure 13 is the process flow diagram of the whole treatment schemees illustrated performed by the read tablet educational devices involved by the embodiment of the present invention 2.
Figure 14 illustrates that mistaken diagnosis position extraction unit carries out the process flow diagram of the detailed process of mistaken diagnosis position extraction process (the step S301 of Figure 13).
Figure 15 shows the representative image of two cases and the example of checkup item.
Figure 16 shows an example of the picture that efferent exports to output medium.
Figure 17 shows an example of the picture that efferent exports to output medium.
Embodiment
Below, accompanying drawing is utilized to be described in detail embodiments of the invention.Further, illustrated below embodiment is preferred object lesson of the present invention.The order etc. of the allocation position of the numerical value shown in following embodiment, shape, material, inscape, inscape and connected mode, step, step is an example, and the present invention is not limited by this.The present invention only limit by claim.Therefore, in the inscape of following embodiment, the inscape not having to record is shown in the independent claims of upper concept of the present invention, is not that the necessity reaching problem of the present invention is formed, therefore adopts preferred formation to be described.
Cause in misdiagnosis pick-up unit involved by embodiments of the invention is, when for ultrasonography, the read tablet generation mistaken diagnosis of CT (ComputedTomography: the computed tomography) image such as image or nuclear magnetic resonance image, from the diagnostic result be transfused to (hereinafter referred to as " read tablet result ") and Diagnostic Time (hereinafter referred to as " read tablet time "), differentiate the reason of mistaken diagnosis be cause because of image model or cause because of diagnostic process, and point out the device of the guidance content conformed to the cause in misdiagnosis of read tablet person.
The cause in misdiagnosis pick-up unit that Yi real of this invention is executed involved by example comprises: read tablet picture cues portion, using during read tablet is reported as being used for the object read tablet picture cues of read tablet image of diagnostic imaging to read tablet person, described read tablet report is described read tablet image and the combination for the determination diagnostic result of described read tablet image, read tablet result obtaining portion, obtain the first read tablet result and read tablet time, described first read tablet is as a result, described read tablet person is for the read tablet result of described object read tablet image, the described read tablet time is, the time used when described read tablet person carries out read tablet for described object read tablet image, read tablet result judging part, by for described object read tablet image determination diagnostic result, compare with the described first read tablet result to be obtained by described read tablet result obtaining portion, judge correcting errors of described first read tablet result, and guidance content Attributions selection portion, when described first read tablet result is judged as mistake by described read tablet result judging part, perform at least one party that (a) first selects process and (b) second to select in process, described first selects process to refer to, when the described read tablet time obtained by described read tablet result obtaining portion is larger than threshold value, select the attribute being used to guide the guidance content of the diagnostic process of the case of the case name shown in described first read tablet result, using the attribute as the described guidance content to described read tablet person's prompting, described second selects process to refer to, when the described read tablet time is below described threshold value, select the attribute being used to guide the guidance content of the image model of the case of the case name shown in described first read tablet result, using the attribute as the described guidance content to described read tablet person's prompting.
Cause in misdiagnosis can utilize the read tablet time to classify.When there is " the corresponding relation mistake of case and diagnostic process ", because read tablet person carries out confirmation while diagnose to diagnostic process seriatim, therefore had feature increases the read tablet time.In addition, when there is " the corresponding relation mistake of case and image model ", can consider that the study of diagnostic process terminates, read tablet person knows diagnostic process.Therefore, because read tablet person is without the need to carrying out the confirmation of diagnostic process, mainly diagnoses according to image model, the read tablet time can be shortened like this.Therefore, when the read tablet time is long, the mistaken diagnosis caused because of " mistake of the corresponding relation of case and diagnostic process " can be judged as YES, when the read tablet time is short, the mistaken diagnosis caused because of " mistake of the corresponding relation of case and image model " can be judged as YES.
Like this, due to can according to the read tablet time, judge it is the mistaken diagnosis because which of diagnostic process and image model occurs, therefore, it is possible to automatically select the attribute of guidance content according to cause in misdiagnosis.According to the attribute of the guidance content selected, read tablet person can select the guidance content can correcting the reason of mistaken diagnosis rightly.Further, can reduce read tablet person will retrieval time of reference guide content when mistaken diagnosis, thus can shorten the learning time of read tablet person.
That is, when the read tablet time is larger than threshold value, can judge it is the mistaken diagnosis caused because of " mistake of the corresponding relation of case and diagnostic process ".Therefore, it is possible to select the attribute being used to guide the guidance content of diagnostic process.Accordingly, read tablet person can select the guidance content can correcting the diagnostic process of the reason becoming mistaken diagnosis rightly.Further, as the guidance content of read tablet person's reference when mistaken diagnosis, can promptly find the guidance content being used to guide diagnostic process, thus the learning time of read tablet person can be shortened.
When the read tablet time is below threshold value, the mistaken diagnosis occurred because of " mistake of the corresponding relation of case and image model " can be judged as YES.Therefore, it is possible to select the attribute being used to guide the guidance content of image model.Accordingly, read tablet person can select the guidance content can correcting the image model of the reason becoming mistaken diagnosis rightly.Further, as the guidance content of read tablet person's reference when mistaken diagnosis, can promptly find the guidance content being used to guide image model, thus the learning time of read tablet person can be shortened.
Further, also can be that described read tablet report also comprises the second read tablet result, and this second read tablet result is the read tablet result having performed read tablet for described read tablet image; Described read tablet picture cues portion, determines described the described read tablet image that diagnostic result described read tablet report consistent with described second read tablet result comprises, is prompted to described read tablet person.
In read tablet report database, there is the characteristic of the camera due to picture noise or read tablet image, and only can not point out the read tablet image of the pathology consistent with determining diagnostic result from image.Such a image is inappropriate as the image of read tablet education, and the image of described read tablet education refers to, only to utilize read tablet image to estimate the image for the purpose of pathology.On the contrary, determining the case that diagnostic result is consistent with the second read tablet result, can be described as the case guaranteeing to point out the pathology identical with determining diagnostic result according to read tablet image.Therefore, by only selecting to determine the read tablet image that diagnostic result is consistent with the second read tablet result, thus the image of the image case required for read tablet education can only be pointed out.
And, above-mentioned cause in misdiagnosis pick-up unit also comprises efferent, this efferent obtain from guidance content database for the case name shown in described first read tablet result case, the guidance content of attribute selected by described guidance content Attributions selection portion, and export the described guidance content obtained, in described guidance content database, store the guidance content of the diagnostic process of the case being used to guide this case name according to each case name and be used to guide the guidance content of image model of case of this case name.
Like this, by obtaining the guidance content of the attribute selected and exporting, thus the time and labor that read tablet person searches guidance content can be reduced.
Further, also can be that described read tablet report also comprises the diagnostic result of each checkup item for multiple checkup item; Described read tablet result obtaining portion, also obtains by described read tablet person each diagnostic result carried out for described multiple checkup item; Described cause in misdiagnosis pick-up unit also comprises mistaken diagnosis position extraction unit, and this mistaken diagnosis position extraction unit extracts described diagnostic result that the report of described read tablet the comprises checkup item different from the described diagnostic result that described read tablet result obtaining portion obtains.
According to such formation, the mistaken diagnosis position of read tablet person can be extracted.
Preferably, above-mentioned cause in misdiagnosis pick-up unit also comprises efferent, this efferent obtains the case for case name shown in described first read tablet result from guidance content database, the guidance content of the attribute selected by described guidance content Attributions selection portion, from the described guidance content obtained, make the guidance content highlighting the position corresponding with the described checkup item that described mistaken diagnosis position extraction unit is extracted, and export the described guidance content made, in described guidance content database, the guidance content of the diagnostic process of the case being used to guide this case name is stored according to each case name, with the guidance content of image model of case being used to guide this case name.
Form according to this, the guidance content of the mistaken diagnosis position highlighting read tablet person can be pointed out.Accordingly, the time of the position detecting read tablet person's mistaken diagnosis can be shortened.Therefore, it is possible to reduce the omission of mistaken diagnosis position and the retrieval time of mistaken diagnosis position, thus the learning efficiency of read tablet person can be improved.
Further, described threshold value also can be different by the case name shown in each described first read tablet result.
By threshold value is different because of each case name, therefore, it is possible to improve the degree of accuracy of the selection of the guidance content attribute that guidance content Attributions selection portion carries out.
Below, cause in misdiagnosis pick-up unit of the present invention and cause in misdiagnosis detection method are described.As an example, be described for the situation of read tablet educational devices cause in misdiagnosis pick-up unit of the present invention being applicable to read tablet person, but, except the read tablet educational devices described in following embodiment, the present invention also can be suitable for.
Such as, also can be in fact when read tablet person is diagnosed by read tablet, carry out the detection of cause in misdiagnosis, and cause in misdiagnosis is prompted to the device of read tablet person.
Below, accompanying drawing is utilized to be described in detail to the read tablet educational devices involved by embodiments of the invention.
(embodiment 1)
Fig. 1 is the block scheme that the characteristic function of the read tablet educational devices 100 illustrated involved by embodiments of the invention 1 is formed.As shown in Figure 1, read tablet educational devices 100 is the devices of pointing out the education content conformed to the read tablet result of read tablet person.Read tablet educational devices 100 comprises: read tablet report database 101, read tablet picture cues portion 102, read tablet result obtaining portion 103, read tablet result judging part 104, guidance content Attributions selection portion 105, guidance content database 106 and efferent 107.
Below, each inscape of the read tablet educational devices 100 shown in Fig. 1 is described in detail in order.
Read tablet report database 101 is the memory storages be made up of such as hard disk, storer etc.Read tablet report database 101 is the databases storing read tablet image and the read tablet information corresponding with this read tablet image pointed out to read tablet person.At this, read tablet image refers to, in order to carry out the image that diagnostic imaging utilizes, the view data deposited in electronic medium is shown.Further, read tablet information refers to, except the read tablet result that read tablet image is shown, also illustrates that the information of the result diagnosed is determined in the biopsy etc. carried out after diagnostic imaging.
Fig. 2 A and Fig. 2 B be respectively illustrate store in read tablet report database 101, as the figure of the ultrasonography of read tablet image 20 and an example of read tablet information 21.Read tablet information 21 comprises: patient ID22, image ID23, determine diagnostic result 24, read tablet person ID25, checkup item judged result 26, image finding 27 and read tablet time 28.
Patient ID22 illustrates the information of the patient for identifying the subject becoming read tablet image.Image ID23 illustrates the information for identifying read tablet image 20.Determine that diagnostic result 24 illustrates the determination diagnostic result of the patient shown in patient ID22.At this, determine that diagnostic result refers to, by microscope to by performing the operation or pathologic finding that biopsy and the subject obtained carry out or other method, and the diagnostic result of real state residing for the patient becoming object learnt.Read tablet person ID25 illustrates the information for identifying read tablet person, and this read tablet person refers to, has carried out the people of read tablet to the read tablet image 20 of image ID23.Checkup item judged result 26 illustrates the information of the diagnostic result for each checkup item (being recited as project 1, project 2 etc. in fig. 2b), and each checkup item described is read tablet image 20 for image ID23 and fixed.Such as, if the read tablet image of image ID23 20 is galactophore image, then checkup item comprise border proterties (clear level and smooth, clear coarse, unintelligible, be difficult to evaluate) and internal echo grade (without, extremely low, low, medium, high) etc.Image finding 27 is the information that the diagnostic result that the read tablet image 20 of the read tablet person of read tablet person ID25 to image ID23 carries out is shown.Image finding 27 is the information that diagnostic result (read tablet result) and diagnosis reason (read tablet reason) comprising name of disease is shown.The read tablet time 28 is the information of the time illustrated from read tablet to read tablet terminates.
Further, when multiple read tablet person has carried out read tablet for the read tablet image 20 of an image ID23, then read tablet person ID25, checkup item judged result 26, image finding 27 and read tablet time 28 has been deposited according to each read tablet person ID25.
Further, although be illustrated possessing read tablet report database 101 for read tablet educational devices 100 in the present embodiment, but the read tablet educational devices that the present invention can be suitable for not limit by such read tablet educational devices.Such as, read tablet report database 101 also can be arranged on the server that is connected with read tablet educational devices by network.
Further, read tablet information 21 also can be comprised in as ancillary data in read tablet image 20.
At this, turn back to the explanation of each inscape of the read tablet educational devices 100 shown in Fig. 1.
Read tablet picture cues portion 102 obtains the read tablet image 20 becoming diagnostic test object from read tablet report database 101.And, read tablet picture cues portion 102, by being shown on the monitors such as not shown liquid crystal display or TV together with List of input seen by the checkup item of read tablet image 20 and image by the read tablet image 20 (object read tablet image) obtained, thus be prompted to read tablet person.Fig. 3 shows the example of the hint image that read tablet picture cues portion 102 carries out.As shown in Figure 3, hint image comprises: the read tablet image 20 of diagnostic test object, using checkup item input area 30 as the List of input of an example and using the List of input of image finding input area 31 as an example, described checkup item input area 30 is answer forms of the diagnostic result for checkup item, and described image finding input area 31 is List of inputs seen by image.The project corresponding with the checkup item judged result 26 of read tablet report database 101 is recorded in checkup item input area 30.In addition, in image finding input area 31, the project corresponding with the image finding 27 of read tablet report database 101 is recorded.
Further, the read tablet image 20 determining that diagnostic result 24 is consistent with image finding 27, when the read tablet image 20 obtaining the object becoming diagnostic test from read tablet report database 101, only can be selected by read tablet picture cues portion 102.There is read tablet image 20 in read tablet report database 101, this read tablet image 20 is characteristics of the camera due to picture noise or read tablet image 20, and only can not indicate the pathology consistent with determining diagnostic result according to image.Such a image is inappropriate as the image of read tablet education, and the image of described read tablet education refers to, only to utilize read tablet image to estimate the image for the purpose of pathology.On the contrary, determining the case that diagnostic result 24 is consistent with image finding 27, can be described as the case guaranteeing to point out the pathology identical with determining diagnostic result according to read tablet image 20.Therefore, by only selecting to determine the read tablet image 20 that diagnostic result 24 is consistent with image finding 27, thus the image of the image case required for read tablet education can only be pointed out.Further, when multiple read tablet person has carried out read tablet for a read tablet image 20, when the image finding 27 of certain read tablet person is consistent with determining diagnostic result 24, also the read tablet image 20 shown in image ID23 can only have been selected.
Read tablet result obtaining portion 103 obtains the read tablet result of the read tablet person for the read tablet image 20 of pointing out in read tablet picture cues portion 102.Such as, obtain the information being imported into checkup item input area 30 and image finding input area 31 by keyboard or mouse etc., and be stored into storer etc.Further, read tablet result obtaining portion 103 obtain read tablet person from read tablet to the time (read tablet time) terminated read tablet.Read tablet result obtaining portion 103, by the information of acquisition and read tablet time, outputs to read tablet result judging part 104 and guidance content Attributions selection portion 105.Further, the read tablet time is measured by the not shown timer being arranged on read tablet educational devices 100.
Read tablet result judging part 104 is by referring to read tablet report database 101, to the read tablet result of the read tablet person obtained from read tablet result obtaining portion 103, compare with the read tablet information 21 being recorded to read tablet report database 101, judge correcting errors of the read tablet result of read tablet person.Specifically, read tablet result judging part 104 is to the input results of the image finding input area 31 to read tablet person obtained from read tablet result obtaining portion 103, compare with the information of the determination diagnostic result 24 of the read tablet image 20 obtained from read tablet report database 101.Read tablet result judging part 104, when both are consistent, is judged as that read tablet result is correct, is judged as that read tablet result is wrong (mistaken diagnosis) in the case of inconsistencies.
The result of the positive erroneous judgement of read tablet result that guidance content Attributions selection portion 105 utilizes the read tablet result and read tablet time that obtain from read tablet result obtaining portion 103 and obtains from read tablet result judging part 104, selects the guidance content attribute to read tablet person's prompting.Further, guidance content Attributions selection portion 105 by select guidance content property notification to efferent 107.In addition, the concrete system of selection for guidance content attribute is treated aftermentioned, is described guidance content attribute at this.
Guidance content attribute refers to, is imparted into two kinds of identifying informations of the guidance content of the correct diagnostic method being used to guide case.Image model (pattern) attribute and this two attribute of diagnostic process attribute is there is particularly in guidance content attribute.The guidance content being endowed image model attribute shows the content relevant to the representative read tablet image 20 for case name.In addition, the guidance content being endowed diagnostic process attribute shows the content relevant to the diagnostic process for case name.Fig. 4 shows an example for the content of the image model attribute of " case name: inocarcinoma " and the content of diagnostic process attribute.As shown in Fig. 4 (a), image model property content 40 is the read tablet images 20 of the exemplary that inocarcinoma is shown.Further, as shown in Fig. 4 (b), diagnostic process property content 41 is the process flow diagrams for diagnosing inocarcinoma.Such as, describe in Fig. 4 (b), when be judged as " obscure boundary is clear " or " sharpness of border is coarse ", " there is fracture front and back ", " rear echo is faint " and " internal echo is extremely low " or " internal echo is high ", be then diagnosed as the diagnostic process of inocarcinoma.
To be described following about guidance content being divided into the reason of these two attributes.
The reason of mistaken diagnosis roughly can be divided into two.First is, the mistake of the case of read tablet person's memory and the corresponding relation of diagnostic process.Second is, the mistake of the case of read tablet person's memory and the corresponding relation of image model.
The reason that cause in misdiagnosis can be categorized as above two kinds is that the learning process of negatoscopy has been divided into the cause in two stages.
At the first half of learning process, read tablet person, after judged other checkup item for read tablet image 20, with reference to diagnostic process while combine with the judged result of checkup item, carries out final diagnosis.Like this, the read tablet person also expertly not grasping read tablet, owing to being progressively with reference to diagnostic process, therefore can spend the read tablet time.On the other hand, although the read tablet person finishing the learning process of first half enters the learning process of latter half, but at the latter half of learning process, read tablet person is after the checkup item judging Ge Do, in brain, the typical image model of each case name is constructed, diagnosing with reference to by while the image model constructed.The read tablet time of the read tablet person of the latter half of study is shorter than the read tablet time of the read tablet person of the first half of study.This is because the read tablet by experiencing repeatedly identical case, thus knowing diagnostic process, therefore not needed the cause with reference to diagnostic process.Therefore, the read tablet person of the latter half of study mainly diagnoses from image model.
That is, the mistaken diagnosis occurred in read tablet is in different learning processes, occurs when obtaining the knowledge of mistake respectively.Therefore, when there is mistaken diagnosis in read tablet educational devices 100, differentiate its reason be because of " case and diagnostic process corresponding on mistake (diagnostic process attribute) " and to occur, or because of " case and image model corresponding on mistake (image model attribute) " and to occur.On this basis, read tablet educational devices 100 by the guidance content of the guidance content attribute corresponding with the reason of mistaken diagnosis is prompted to read tablet person, to provide the content conformed to the cause in misdiagnosis of read tablet person.
Two above-mentioned diagnostic process can utilize the read tablet time to classify.Fig. 5 shows the histogram of the exemplary of the read tablet time of the dept. of radiology of certain hospital.In addition, in the histogram of Fig. 5, carry out approximate frequency (read tablet number of packages) with curve waveform.As shown in Figure 5, there are two peak values, can judge that the peak value of the side that the read tablet time is short is the diagnosis carried out according to image model in histogrammic waveform, the peak value of the side that the read tablet time is long judges according to diagnostic process the diagnosis carried out.The difference of such a time response, occurs because of the difference of the learning process of read tablet as described.Specifically the presence or absence of the reference of diagnostic process is then a large factor.
By utilizing the characteristic of such read tablet time, thus can classify to the mistaken diagnosis factor of read tablet doctor when mistaken diagnosis.Such as, the read tablet of carrying out at short read tablet time A, as a result, when there occurs mistaken diagnosis, is because the misjudgment of the image model of this read tablet person occurs.Therefore, be the image model that prompting is correct as guidance content, need the image model correcting the mistake of constructing in the brain of read tablet person.On the other hand, the read tablet of carrying out at long read tablet time B as a result, when there occurs mistaken diagnosis, be that the mistake judged because of diagnostic process occurs.Therefore, the content of the diagnostic process carried out for correcting the mistake that read tablet person remembers is needed to instruct.
Like this, by guidance content being divided into two attributes, thus the guidance content conformed to the essential factor of mistaken diagnosis can be pointed out.Accordingly, the time of oneself retrieval guidance content can be reduced and read the time of unnecessary guidance content, thus the learning time of read tablet person can be shortened.
At this, turn back to the explanation of each inscape to the read tablet educational devices 100 shown in Fig. 1.
Guidance content database 106 is, respectively the database of with image model attribute with diagnostic process attribute this two the attributes relevant guidance content of record selected by guidance content Attributions selection portion 105.Fig. 6 is the example instructing content data base 106.As shown in Figure 6, guidance content database 106 comprises contents attribute 60, case name 61 and content ID62.Content ID62 in order to obtain content ID62 simply according to contents attribute 60 and case name 61, and is classified as detail by guidance content database 106.Such as, contents attribute 60 is diagnostic process attributes, and when case name 61 is inocarcinoma, the content ID62 of guidance content is F_001.In addition, corresponding with content ID62 guidance content is stored in guidance content database 106.But, guidance content also can be stored in guidance content database 106 and such as can be stored in outside server.
Efferent 107 by referring to guidance content database 106, thus from the content ID that the case name that guidance content database 106 to have obtained with the contents attribute selected by guidance content Attributions selection portion 105 with read tablet person's mistaken diagnosis conforms to.Further, the guidance content corresponding with the content ID obtained is outputted to output medium by efferent 107.Output medium is such as the monitor such as liquid crystal display, TV.
Then the work of the read tablet educational devices 100 with above formation is described.
Fig. 7 is the process flow diagram of all flow processs of the process illustrated performed by read tablet educational devices 100.
First, read tablet picture cues portion 102 obtains the read tablet image 20 of the object becoming diagnostic test from read tablet report database 101.The read tablet image 20 of acquisition is presented on the monitors such as not shown liquid crystal display, TV, to be prompted to read tablet person (step S101) by read tablet picture cues portion 102 together with List of input seen by the checkup item of read tablet image 20 and image.The read tablet image 20 becoming object can be selected by read tablet person, also can choose at random.
Read tablet result obtaining portion 103 obtain pointed out by read tablet picture cues portion 102, for the read tablet result of the read tablet person of read tablet image 20.Such as, the information inputted by keyboard, mouse etc. is stored into storer etc. by read tablet result obtaining portion 103.Further, the input of acquisition is informed to read tablet result judging part 104 and guidance content Attributions selection portion 105 (step S102) by read tablet result obtaining portion 103.Specifically, read tablet result obtaining portion 103 obtains from read tablet picture cues portion 102, is imported into the information of checkup item input area 30 and image finding input area 31 respectively.Further, read tablet result obtaining portion 103 obtains the read tablet time.
Read tablet result judging part 104, by referring to read tablet report database 101, compares the read tablet information 21 recorded in the read tablet result of the read tablet person obtained from read tablet result obtaining portion 103 and read tablet report database 101.Read tablet result judging part 104, according to comparative result, judges correct errors (the step S103) of the read tablet result of read tablet person.Specifically, read tablet result judging part 104 to obtain from read tablet result obtaining portion 103 by read tablet person be input to image finding input area 31 input results, compare with the information of the determination diagnostic result 24 of the read tablet image 20 obtained from read tablet report database 101.Read tablet result judging part 104 is judged as that when both are consistent read tablet result is correct, is judged as mistake (mistaken diagnosis) by read tablet result in the case of inconsistencies.Such as, for read tablet image A, the image finding of the read tablet person obtained in step s 102 is input as " inocarcinoma ", the determination diagnostic result obtained from read tablet report database 101 is for " inocarcinoma ", because both are consistent, be therefore judged as it not being mistaken diagnosis (correctly).On the contrary, for read tablet image A, the image finding of the read tablet person obtained in step s 102 is input as " inocarcinoma ", and when the determination obtained from read tablet report database 101 is diagnosed as beyond " inocarcinoma ", because both are inconsistent, is therefore judged as mistaken diagnosis.
Further, when the diagnosis obtained from step S102 is called multiple, if one of them is consistent with the determination diagnostic result obtained from read tablet report database 101, also can be judged as correct.
Guidance content Attributions selection portion 105 when obtain from read tablet result judging part 104 be the judgement of mistaken diagnosis ("Yes" of step S104), obtain the input results and read tablet time that are input to image finding input area 31 respectively from read tablet result obtaining portion 103.Further, guidance content Attributions selection portion 105 utilizes the read tablet time to select guidance content attribute, by the guidance content property notification of selection to efferent 107 (step S105).About guidance content Attributions selection process (step S105) treat in detail aftermentioned.
Finally, efferent 107 by referring to guidance content database 106, the content ID that the case name obtained with the guidance content attribute selected by guidance content Attributions selection portion 105 with read tablet person's mistaken diagnosis from guidance content database 106 conforms to.Further, the guidance content corresponding with the content ID obtained obtains by efferent 107 from guidance content database 106, and exports to output medium (step S106).
Below guidance content Attributions selection process (the step S105 of Fig. 7) is described in detail.Fig. 8 is the process flow diagram of the detailed process that the guidance content Attributions selection process (the step S105 of Fig. 7) undertaken by guidance content Attributions selection portion 105 is shown.Below, the guidance content attribute selection method of Fig. 8 to the read tablet time that make use of read tablet person is utilized to be described.
First, guidance content Attributions selection portion 105 obtains the image finding (step S201) inputted by read tablet person from read tablet result obtaining portion 103.
Guidance content Attributions selection portion 105 obtains the read tablet time (step S202) of read tablet person from read tablet result obtaining portion 103.Further, the read tablet time of read tablet person can be measured by the timer being arranged on read tablet educational devices 100 inside.Such as, when starting read tablet (during prompting read tablet image), user presses the beginning key be displayed on picture, and when terminating read tablet, user presses the end key be displayed on picture.Key from pressing also can obtain to the time of pressing end key as the read tablet time by guidance content Attributions selection portion 105.
Guidance content Attributions selection portion 105 calculates the threshold value (step S203) of the read tablet time for judging guidance content attribute.The calculation method of threshold value such as can according to the read tablet time of recorded data in read tablet report database 101, make the histogram of read tablet time, discrimination threshold is utilized to select method (with reference to non-patent literature: " portrait process Ha Application De Block ッ Network (image processing handbook) ", pp.278, clear rolling hall, 1992) threshold value of read tablet time is obtained.Accordingly, the part of the trough in the histogram shown in Fig. 5 between two peak values can be set the threshold to.
In addition, each case name that the threshold value of read tablet time also can judge according to read tablet person is obtained.The Frequency of diagnostic process or the Frequency of case are different because examining the position of object or case name.Therefore, the situation that read tablet time difference is different is also had.Such as, in the ultrasonic image diagnotor of mammary gland, inocarcinoma and the ILC of a part can be listed as the case name that diagnostic process is short.These tumours, owing to being only just can judge case name according to the proterties of boudary portion, therefore judge that the time of case name is also short than other case name.On the other hand, in the ultrasonic image diagnotor of same mammary gland, a part of packing and mucous carcinoma etc. can be listed as the case name that diagnostic process is long.These tumours due to be need to utilize boudary portion and shape, case name that aspect ratio can judge, therefore than the inocarcinoma of a part and the read tablet time of ILC long.
Further, also can because of the Frequency of case name the read tablet time different.Such as, the Frequency of " inocarcinoma " in breast disease is about 30%, and the Frequency of " cephaloma " is about 0.5%.The high case of Frequency, owing to can frequently occur clinically, therefore, it is possible to diagnose as soon as possible, can shorten the read tablet time compared with the case that Frequency is low.
Therefore, by asking threshold value according to each position or each case name, thus the degree of accuracy of attributive classification can be improved.
Further, the threshold value of read tablet time be with the renewal of read tablet report database 101 while and calculated, therefore can be stored in read tablet report database 101.Further, calculating of this threshold value also can be performed by guidance content Attributions selection portion 105, also can be performed by other handling part.Accordingly, read tablet person can carry out calculating of threshold value when carrying out checkup item input etc. at every turn.Therefore, it is possible to shorten the processing time of read tablet educational devices 100, and with the shorter time, guidance content can be prompted to read tablet person.
Guidance content Attributions selection portion 105 differentiates that whether the read tablet time of the read tablet person obtained in step S202 is than the threshold value calculated in step S203 large (step S204).When the read tablet time is larger than threshold value ("Yes" of step S204), guidance content Attributions selection portion 105 selects diagnostic process attribute using the attribute (step S205) as guidance content.On the other hand, when the read tablet time is below threshold value ("No" of step S204), guidance content Attributions selection portion 105 selects image model attribute using the attribute (step S206) as guidance content.
By performing the process of above step S201 ~ S206, thus the attribute of the guidance content corresponding with the cause in misdiagnosis of read tablet person can be selected by guidance content Attributions selection portion 105.
Fig. 9 shows when image model attribute is selected in guidance content Attributions selection portion 105, is outputted to an example of the picture of output medium by efferent 107.As shown in Fig. 9 (a), the read tablet result (read tablet person's answer) of the wrongheaded read tablet image of efferent 107 couples of read tablet persons, read tablet person and determine that diagnostic result (correctly) is pointed out.Further, as shown in Fig. 9 (b), efferent 107, while carrying out this prompting, is also pointed out with the representative image that read tablet person answers corresponding case name.When image model attribute is selected, can consider that read tablet person is the diagnostic process knowing " inocarcinoma ".Therefore, such read tablet person mainly carries out diagnosing according to image model, and mistake has appearred in read tablet person in the correspondence of the image model for " inocarcinoma ", thus there occurs mistaken diagnosis.Therefore, by the representative image of prompting for " inocarcinoma " of answering as read tablet person, thus the representative image of " inocarcinoma " of read tablet person's wrong identification can be corrected.
Further, Figure 10 shows guidance content Attributions selection portion 105 when have selected diagnostic process attribute, an example of the picture exported to output medium by efferent 107.As shown in Figure 10 (a), efferent 107 is same with Fig. 9 (a) Suo Shi, to the read tablet result (read tablet person's answer) of the wrongheaded read tablet image of read tablet person, read tablet person and determine that diagnostic result (correctly) is pointed out.Further, as shown in Figure 10 (b), efferent 107, while carrying out this prompting, is also pointed out with the diagnostic process that read tablet person answers corresponding case name.In the example shown in Figure 10, be because having occurred mistake in the correspondence of the diagnostic process of the read tablet person for " inocarcinoma ", thus having there occurs mistaken diagnosis.Therefore, by the correct diagnostic process of prompting for " inocarcinoma " of answering as read tablet person, thus the knowledge of the diagnostic process of " inocarcinoma " of read tablet person's wrong identification can be corrected.
As described above, by performing the process of the step S101 ~ step S106 shown in Fig. 7, thus read tablet educational devices 100 can point out the guidance content corresponding with the cause in misdiagnosis of read tablet person.Therefore, learning time is shortened, thus can carry out the study of high efficiency read tablet method.
That is, by the read tablet educational devices 100 involved by the present embodiment, utilize the read tablet time of read tablet person to judge cause in misdiagnosis, thus can automatically select the guidance content corresponding with the cause in misdiagnosis judged.Therefore, unwanted guidance content can not be prompted to read tablet person, thus read tablet method can be learnt expeditiously.
(embodiment 2)
Below the read tablet educational devices involved by embodiments of the invention 2 is described.
As previously discussed, read tablet educational devices 100 involved by embodiment 1 is by utilizing the read tablet time, the cause in misdiagnosis of read tablet person is categorized as the some of the attribute of " diagnostic process attribute " and " image model attribute " these two kinds, thus the guidance content of answering with Attribute Relative can be pointed out.Further, the read tablet educational devices involved by the present embodiment, also to the content instructed when read tablet person's mistaken diagnosis, is pointed out after emphasizing to become the position (mistaken diagnosis position) of cause in misdiagnosis.
The background of the present embodiment problem to be solved as described below.Such as, when " palilate tubular adenocarcinoma " mistaken diagnosis is " inocarcinoma " by read tablet person in the ultrasonic image diagnotor carrying out mammary gland, the diagnostic process of " inocarcinoma " is (difference) with the difference of the diagnostic process of " palilate tubular adenocarcinoma ", the many-side such as " internal echo ", " rear echo " and " border proterties ".In order to make read tablet person correctly learn read tablet method, need to identify all difference.But such as when merely pointing out the diagnostic process of inocarcinoma and palilate tubular adenocarcinoma, the difference part of meeting over sight (OS) two diagnostic process, there will be the possibility that can not correctly learn.Further, the behavior itself finding the difference of two diagnostic process also can increase learning time, result, can reduce learning efficiency equally.
For such problem, the read tablet educational devices involved by the present embodiment is pointed out guidance content after can emphasizing the mistaken diagnosis position of read tablet person, therefore, it is possible to improve learning efficiency.
Referring to Figure 11, each formation of the read tablet educational devices involved by the present embodiment is described successively.
(each explanation formed of embodiment 2)
Figure 11 is the block scheme with distinctive function formation of the read tablet educational devices 200 illustrated involved by embodiments of the invention 2.In fig. 11, give identical symbol for the inscape identical with Fig. 1 and omit the description.
Read tablet educational devices 200 comprises: read tablet report database 101, read tablet picture cues portion 102, read tablet result obtaining portion 103, read tablet result judging part 104, guidance content Attributions selection portion 105, guidance content database 106, efferent 107 and mistaken diagnosis position extraction unit 201.
Read tablet educational devices 200 shown in Figure 11 is possess mistaken diagnosis position extraction unit 201 with the difference of the read tablet educational devices 100 shown in Fig. 1, this mistaken diagnosis position extraction unit 201 from obtained by read tablet result obtaining portion 103, the result that is imported into checkup item input area 30, extract the mistaken diagnosis position of read tablet person.
Mistaken diagnosis position extraction unit 201 is such as be made up of CPU and the storer etc. of depositing the program performed by CPU.In the checkup item judged result 26 comprised the judged result being imported into checkup item input area 30 that mistaken diagnosis position extraction unit 201 obtains from read tablet result obtaining portion 103 and the read tablet information 21 being stored in read tablet report database 101, extract the mistaken diagnosis position of read tablet person, and inform efferent 107.Concrete mistaken diagnosis position extracting method is treated aftermentioned.
Mistaken diagnosis position is defined as, and there occurs the region in the checkup item of mistaken diagnosis or representative image in read tablet process.Specifically, read tablet process roughly can be divided into " visual " and " diagnosis " these two processes, mistaken diagnosis position in visual process is corresponding with the specific image-region on read tablet image 20, and the mistaken diagnosis position in diagnostic procedure is corresponding with the specific checkup item on diagnostic process.Figure 12 A and Figure 12 B shows an example of the mistaken diagnosis position in breast ultrasound ripple image.When the mistaken diagnosis position that mistaken diagnosis position extraction unit 201 is extracted read tablet person is the internal echo proterties of tumour, as illustrated in fig. 12, the mistaken diagnosis position on read tablet image 20 refers to the mistaken diagnosis position 70 as corresponding image-region.Further, as shown in Figure 12 B, the mistaken diagnosis position on diagnostic process refers to the mistaken diagnosis position 71 corresponding with the checkup item of mistaken diagnosis.
By pointing out these mistaken diagnosis positions clearly, thus the time of the position detecting the mistaken diagnosis of read tablet person institute can be shortened, therefore, it is possible to improve learning efficiency.
While the process flow diagram of reference Figure 13, to being described in whole treatment schemees of read tablet educational devices 200 execution shown in Figure 11.
Figure 13 is the process flow diagram of all flow processs of process illustrated performed by read tablet educational devices 200.Further, identical symbol is given for the treatment step identical with the process of the read tablet educational devices 100 in the embodiment 1 shown in Fig. 7 in fig. 13.
In the read tablet educational devices 200 involved by the present embodiment, what obtain from read tablet result obtaining portion 103 is imported into the judged result of checkup item input area 30, extract the process of the mistaken diagnosis position of read tablet person, different from the process in the read tablet educational devices 100 of embodiment 1.But other process is identical with the process of the read tablet educational devices 100 of embodiment 1.Specifically, in fig. 13, the process of the step S101 performed by read tablet educational devices 200 ~ S105 is identical with the process of the read tablet educational devices 100 of the embodiment 1 shown in Fig. 7, therefore omits the description.
Mistaken diagnosis position extraction unit 201 utilizes the judged result being imported into checkup item input area 30 obtained from read tablet result obtaining portion 103, extracts the mistaken diagnosis position (step S301) of read tablet person.
Efferent 107 is same with the step S106 shown in Fig. 7, obtains guidance content, and export to output medium from guidance content database 106.But, when efferent 107 exports guidance content, the basis highlighting the mistaken diagnosis position that mistaken diagnosis position extraction unit 201 is extracted carries out exporting (step S302).Treat aftermentioned about the object lesson emphasized.
Figure 14 is the process flow diagram of the detailed process that the process (the step S301 of Figure 13) undertaken by mistaken diagnosis position extraction unit 201 is shown.The extracting method of Figure 14 to the mistaken diagnosis position of read tablet person is below utilized to be described.
First, mistaken diagnosis position extraction unit 201 obtains the judged result (step S401) being imported into checkup item input area 30 from read tablet result obtaining portion 103.
Mistaken diagnosis position extraction unit 201 obtains checkup item judged result 26 from read tablet report database 101, and this checkup item judged result 26 has the image finding 27 (step S402) identical with the determination diagnostic result 24 corresponding to the read tablet image of the object becoming diagnosis.
Mistaken diagnosis position extraction unit 201 be extracted in step S401 obtain be input to the judged result of checkup item input area 30, the checkup item (step S403) different from the checkup item judged result 26 obtained in step S402 by read tablet person.Namely, mistaken diagnosis position extraction unit 201 extracts different checkup items using as mistaken diagnosis position.
Figure 15 shows " A cancer " and the representative image of " B cancer " and the example of checkup item.The different disposal of Figure 15 to step S403 is below utilized to be described.Now with for the read tablet object images being correctly diagnosed as B cancer, and read tablet person's mistaken diagnosis be A cancer is example.Now, in order to being judged as each checkup item that A cancer is carried out, determine which part is mistake have learned, as long as the checkup item carried out the mistaken diagnosis read tablet person that is A cancer extracts the different checkup item of judged result between the checkup item of the B cancer correctly diagnosed.In the example of Figure 15, between the checkup item of the checkup item that the read tablet person that mistaken diagnosis is A cancer carries out and the correct B cancer diagnosed, the checkup item that judged result is different is internal echo 80 and rear echo 81, and the checkup item that these judged results are different is extracted as mistaken diagnosis position.That is, about internal echo 80, the diagnostic result due to A cancer is " low ", and the diagnostic result Wei “ Very of B cancer is low ", therefore, internal echo 80 is extracted as mistaken diagnosis position.Further, about rear echo 81, the diagnostic result due to A cancer is " weakening ", and the diagnostic result of B cancer is " constant ", and therefore rear echo 81 is extracted as mistaken diagnosis position.
By performing the process of above step S401 ~ S403, mistaken diagnosis position extraction unit 201 can extract the mistaken diagnosis position of read tablet person.
The process (the step S302 of Figure 13) carried out about efferent 107 will be described with object lesson.
Figure 16 shows when mistaken diagnosis position extraction unit 201 extracts mistaken diagnosis position, is exported to an example of the picture of output medium by efferent 107.As shown in figure 16, efferent 107, in the representative image of the case name of read tablet person institute mistaken diagnosis, emphasizes rear prompting to becoming the image-region corresponding with the mistaken diagnosis position of the difference of the checkup item of correct case.Under these circumstances, between " inocarcinoma " and " infiltration ductal carcinomas of breast ", for the image-region of " rear echo " and " internal echo " meeting the different checkup item of judged result, by pointing out with arrow, thus realize being highlighted.Therefore, when pointing out the representative image for " inocarcinoma " of answering as read tablet person, the image-region of read tablet person's wrong identification can automatically be pointed out.In addition, the positional information of the image-region emphasized also can be corresponding with checkup item in advance, is stored in guidance content database 106.Efferent 107, according to the mistaken diagnosis position (checkup item) of being extracted by mistaken diagnosis position extraction unit 201, by referring to guidance content database 106, obtains the positional information of the image-region emphasized, the positional information according to obtaining is highlighted.Further, the positional information of the image-region emphasized also can be stored in beyond guidance content database 106.Further, the positional information of the image-region emphasized also can be stored in any one place.In this case, efferent 107, by carrying out image procossing, also can detect the image-region emphasized.
Further, Figure 17 shows when extracting mistaken diagnosis position by mistaken diagnosis position extraction unit 201, is outputted to an example of the picture of output medium by efferent 107.As shown in figure 17, efferent 107 is in read tablet person's mistaken diagnosis in the diagnostic process of case name, and prompting becomes the diagnostic process region with the difference of the checkup item of correct case.Also same with Figure 16 in this case, for the diagnostic process region of " the rear echo " and " internal echo " that meet as the different checkup item of judged result between " inocarcinoma " from " infiltration ductal carcinomas of breast ", by irising out with dotted line and pointing out with arrow, thus can be highlighted.Accordingly, when pointing out the diagnostic process for " inocarcinoma " of answering as read tablet person, the diagnostic process region of read tablet person's wrong identification can automatically be pointed out.
In sum, by performing the process of step S101 ~ step S106 and step S301, read tablet educational devices 200 can by the mistaken diagnosis position indicating of read tablet person to efferent 107, thus the leakage of mistaken diagnosis position is seen and retrieval time can both reduce, therefore, it is possible to make learning efficiency improve.
Be illustrated read tablet educational devices involved in the present invention according to embodiment above, but, the present invention not limit by these embodiments.When not unconventional purport of the present invention, the various distortion that the present embodiment is performed that those skilled in the art can expect, and carry out the mode such as combining all within the scope of the present invention to the inscape in different embodiments.
In addition, the necessary inscape of read tablet educational devices involved in the present invention is read tablet picture cues portion 102, read tablet result obtaining portion 103, read tablet result judging part 104 and guidance content Attributions selection portion 105, and inscape in addition also can possess.
Further, each above-mentioned device can be specifically the computer system be made up of microprocessor, ROM, RAM, hard disk unit, display unit, keyboard, mouse etc.In RAM or hard disk unit, memory has computer program.Microprocessor is by carrying out work according to computer program, thus each device can realize its function.At this, computer program is to realize the function specified, and is combined by multiple instruction code for computing machine indicator.
Further, part or all forming the inscape of each above-mentioned device also can be made up of a system LSI (LargeScaleIntegration: large scale integrated circuit).System LSI is by super multi-functional LSI on a single die integrated and manufactured for multiple constituting portion, specifically comprises microprocessor, ROM, RAM etc. and the computer system be configured.In RAM, memory has computer program.Carry out work by microprocessor according to computer program, thus system LSI can realize its function.
And part or all forming the inscape of each above-mentioned device can by the module composition of the IC-card or monomer that can be loaded and unloaded on each device.IC-card or module are the computer systems be made up of microprocessor, ROM, RAM etc.IC-card or module also can comprise above-mentioned super multi-functional LSI.Carry out work by microprocessor according to computer program, thus IC-card or module can realize its function.This IC-card or module also can have against tampering.
Further, the present invention also can be above shown method.Further, also can realizing as the computer program making computing machine perform these methods, also can be the digital signal be made up of described computer program.
And, the present invention also can by described computer program or described digital signal record in the nonvolatile recording medium of embodied on computer readable, and these nonvolatile recording mediums are such as floppy disk, hard disk, CD-ROM, MO, DVD, DVD-ROM, DVD-RAM, BD (Blu-ray (registered trademark) Disc), semiconductor memory etc.Further, also can realize as the described digital signal be recorded in these nonvolatile recording mediums.
Further, the present invention can by electrical communication circuit, wireless or wire communication circuit, be that the network and data broadcast etc. of representative transmits described computer program or described digital signal with the Internet.
Further, the present invention can be the computer system possessing microprocessor and storer, and described storer stores above computer program, and described microprocessor carrys out work according to described computer program.
Further, described program or described digital signal record can be transmitted to described nonvolatile recording medium, or described program or described digital signal can be transmitted by described network etc., thus can be performed by independently other computer system.
And the above embodiments and above-mentioned variation can distinguish independent assortment.
The present invention can utilize as the device etc. detecting cause in misdiagnosis from the read tablet input of read tablet person.
symbol description
20 read tablet images
21 read tablet information
22 patient ID
23 image ID
24 determine diagnostic result
25 read tablet person ID
26 checkup item judged results
27 image findings
28 read tablet times
40 image model property content
41 diagnostic process property content
60 contents attributes
61 case names
62 content ID
70,71 mistaken diagnosis positions
80 internal echos
81 rear echoes
100,200 read tablet educational devices
101 read tablet report databases
102 read tablet picture cues portions
103 read tablet result obtaining portion
104 read tablet result judging parts
105 guidance content Attributions selection portions
106 guidance content databases
107 efferents
201 mistaken diagnosis position extraction units
Claims (7)
1. a cause in misdiagnosis pick-up unit, comprising:
Read tablet picture cues portion, using during read tablet is reported as being used for the object read tablet picture cues of read tablet image of diagnostic imaging to read tablet person, described read tablet report is described read tablet image and the combination for the determination diagnostic result of described read tablet image;
Read tablet result obtaining portion, obtain the first read tablet result and read tablet time, described first read tablet is as a result, described read tablet person is for the read tablet result of described object read tablet image, the described read tablet time is, the time used when described read tablet person carries out read tablet for described object read tablet image;
Read tablet result judging part, by comparing with the described first read tablet result obtained by described read tablet result obtaining portion the determination diagnostic result for described object read tablet image, judges correcting errors of described first read tablet result; And
Guidance content Attributions selection portion, when described first read tablet result is judged as mistake by described read tablet result judging part, perform at least one party that (a) first selects process and (b) second to select in process, described first selects process to refer to, when the described read tablet time obtained by described read tablet result obtaining portion is larger than threshold value, select the attribute being used to guide the guidance content of the diagnostic process of the case of the case name shown in described first read tablet result, using the attribute as the guidance content to described read tablet person's prompting, described second selects process to refer to, when the described read tablet time is below described threshold value, select the attribute being used to guide the guidance content of the image model of the case of the case name shown in described first read tablet result, using the attribute as the described guidance content to described read tablet person's prompting.
2. cause in misdiagnosis pick-up unit as claimed in claim 1,
Described read tablet report also comprises the second read tablet result, and this second read tablet result is the read tablet result having performed read tablet for described read tablet image;
Described read tablet picture cues portion, determines described the described read tablet image that diagnostic result described read tablet report consistent with described second read tablet result comprises, is prompted to described read tablet person.
3. cause in misdiagnosis pick-up unit as claimed in claim 1 or 2,
Also comprise efferent, this efferent obtain from guidance content database for the case name shown in described first read tablet result case, the guidance content of attribute selected by described guidance content Attributions selection portion, and export the described guidance content obtained, in described guidance content database, store the guidance content of the diagnostic process of the case being used to guide this case name according to each case name and be used to guide the guidance content of image model of case of this case name.
4. cause in misdiagnosis pick-up unit as claimed in claim 1 or 2,
Described read tablet report also comprises the diagnostic result of each checkup item for multiple checkup item;
Described read tablet result obtaining portion, also obtains by described read tablet person each diagnostic result carried out for described multiple checkup item;
Described cause in misdiagnosis pick-up unit also comprises mistaken diagnosis position extraction unit, and this mistaken diagnosis position extraction unit extracts described diagnostic result that the report of described read tablet the comprises checkup item different from the described diagnostic result that described read tablet result obtaining portion obtains.
5. cause in misdiagnosis pick-up unit as claimed in claim 4,
Also comprise efferent, this efferent obtains the case for case name shown in described first read tablet result from guidance content database, the guidance content of the attribute selected by described guidance content Attributions selection portion, be produced in the described guidance content of acquisition the guidance content highlighting the position corresponding with the described checkup item that described mistaken diagnosis position extraction unit is extracted, and export the described guidance content made, in described guidance content database, store the guidance content of the diagnostic process of the case being used to guide this case name according to each case name and be used to guide the guidance content of image model of case of this case name.
6. cause in misdiagnosis pick-up unit as claimed in claim 1,
Described threshold value is different by each case name shown in described first read tablet result.
7. a cause in misdiagnosis detection method, comprising:
Read tablet picture cues step, by computing machine, using during read tablet is reported as being used for the object read tablet picture cues of read tablet image of diagnostic imaging to read tablet person, described read tablet report is described read tablet image and the combination for the determination diagnostic result of described read tablet image;
Read tablet result obtains step, by computing machine, obtain the first read tablet result and read tablet time, described first read tablet result is, described read tablet person is for the read tablet result of described object read tablet image, the described read tablet time is, the time used when described read tablet person carries out read tablet for described object read tablet image;
Read tablet result determining step, by computing machine, by for described object read tablet image determination diagnostic result with obtain the described first read tablet result that step obtains in described read tablet result and compare, judge correcting errors of described first read tablet result; And
Guidance content Attributions selection step, when described in described read tablet result determining step, the first read tablet result is judged as mistake, the at least one party that (a) first select process and (b) second to select in process is performed by computing machine, described first selects process to refer to, when the described read tablet time that described read tablet result obtains step acquisition is larger than threshold value, select the attribute being used to guide the guidance content of the diagnostic process of the case of the case name shown in described first read tablet result, using the attribute as the guidance content to described read tablet person's prompting, described second selects process to refer to, when the described read tablet time is below described threshold value, select the attribute being used to guide the guidance content of the image model of the case of the case name shown in described first read tablet result, using the attribute as the described guidance content to described read tablet person's prompting.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2010-200373 | 2010-09-07 | ||
| JP2010200373 | 2010-09-07 | ||
| PCT/JP2011/004780 WO2012032734A1 (en) | 2010-09-07 | 2011-08-29 | Device for detecting causes of misdiagnoses and method for detecting causes of misdiagnoses |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102741849A CN102741849A (en) | 2012-10-17 |
| CN102741849B true CN102741849B (en) | 2016-03-16 |
Family
ID=45810345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201180007768.6A Active CN102741849B (en) | 2010-09-07 | 2011-08-29 | Cause in misdiagnosis pick-up unit and cause in misdiagnosis detection method |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20120208161A1 (en) |
| JP (1) | JP4945705B2 (en) |
| CN (1) | CN102741849B (en) |
| WO (1) | WO2012032734A1 (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9355569B2 (en) * | 2012-08-30 | 2016-05-31 | Picmonic Inc. | Systems, methods, and computer program products for providing a learning aid using pictorial mnemonics |
| CN102982242A (en) * | 2012-11-28 | 2013-03-20 | 徐州医学院 | Intelligent medical image read error reminding system |
| CN103595775B (en) | 2013-11-04 | 2018-01-19 | 惠州Tcl移动通信有限公司 | The sharing method and system of media file |
| US10901978B2 (en) * | 2013-11-26 | 2021-01-26 | Koninklijke Philips N.V. | System and method for correlation of pathology reports and radiology reports |
| WO2015134668A1 (en) * | 2014-03-04 | 2015-09-11 | The Regents Of The University Of California | Automated quality control of diagnostic radiology |
| JP6525527B2 (en) * | 2014-08-07 | 2019-06-05 | キヤノン株式会社 | Diagnostic reading report creation support device, diagnostic reading report creation support method and program |
| JP2016177418A (en) * | 2015-03-19 | 2016-10-06 | コニカミノルタ株式会社 | Image reading result evaluation device and program |
| JP6473124B2 (en) * | 2015-12-09 | 2019-02-20 | 株式会社ジェイマックシステム | Interpretation training support device, interpretation training support method, and interpretation training support program |
| US11108575B2 (en) | 2017-07-26 | 2021-08-31 | Amazon Technologies, Inc. | Training models for IOT devices |
| US11902396B2 (en) | 2017-07-26 | 2024-02-13 | Amazon Technologies, Inc. | Model tiering for IoT device clusters |
| US10980085B2 (en) | 2017-07-26 | 2021-04-13 | Amazon Technologies, Inc. | Split predictions for IoT devices |
| WO2019068925A1 (en) * | 2017-10-06 | 2019-04-11 | Koninklijke Philips N.V. | Addendum-based report quality scorecard generation |
| US11611580B1 (en) | 2020-03-02 | 2023-03-21 | Amazon Technologies, Inc. | Malware infection detection service for IoT devices |
| US11489853B2 (en) | 2020-05-01 | 2022-11-01 | Amazon Technologies, Inc. | Distributed threat sensor data aggregation and data export |
| US11989627B1 (en) | 2020-06-29 | 2024-05-21 | Amazon Technologies, Inc. | Automated machine learning pipeline generation |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101706843A (en) * | 2009-11-16 | 2010-05-12 | 杭州电子科技大学 | Interactive film Interpretation method of mammary gland CR image |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6301462B1 (en) * | 1999-01-15 | 2001-10-09 | Unext. Com | Online collaborative apprenticeship |
| JP4635681B2 (en) * | 2005-03-29 | 2011-02-23 | コニカミノルタエムジー株式会社 | Medical image interpretation system |
| JP2007275408A (en) * | 2006-04-10 | 2007-10-25 | Fujifilm Corp | Similar image retrieval device, method, and program |
| JP5337992B2 (en) * | 2007-09-26 | 2013-11-06 | 富士フイルム株式会社 | Medical information processing system, medical information processing method, and program |
| JP2009078085A (en) * | 2007-09-27 | 2009-04-16 | Fujifilm Corp | Medical image processing system, medical image processing method and program |
| JP2009082182A (en) * | 2007-09-27 | 2009-04-23 | Fujifilm Corp | Examination work support apparatus and method and examination work support system |
| JP2010057727A (en) * | 2008-09-04 | 2010-03-18 | Konica Minolta Medical & Graphic Inc | Medical image reading system |
| US20110039249A1 (en) * | 2009-08-14 | 2011-02-17 | Ronald Jay Packard | Systems and methods for producing, delivering and managing educational material |
-
2011
- 2011-08-29 WO PCT/JP2011/004780 patent/WO2012032734A1/en active Application Filing
- 2011-08-29 CN CN201180007768.6A patent/CN102741849B/en active Active
- 2011-08-29 JP JP2011553996A patent/JP4945705B2/en active Active
-
2012
- 2012-04-24 US US13/454,239 patent/US20120208161A1/en not_active Abandoned
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101706843A (en) * | 2009-11-16 | 2010-05-12 | 杭州电子科技大学 | Interactive film Interpretation method of mammary gland CR image |
Non-Patent Citations (1)
| Title |
|---|
| 无胆总管胰管扩张的胰腺癌CT误诊30例分析;杨鸿翔;《内蒙古医学杂志》;20080531;第40卷(第5期);第591-593页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102741849A (en) | 2012-10-17 |
| US20120208161A1 (en) | 2012-08-16 |
| WO2012032734A1 (en) | 2012-03-15 |
| JPWO2012032734A1 (en) | 2014-01-20 |
| JP4945705B2 (en) | 2012-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102741849B (en) | Cause in misdiagnosis pick-up unit and cause in misdiagnosis detection method | |
| Baloescu et al. | Automated lung ultrasound B-line assessment using a deep learning algorithm | |
| Metz | Receiver operating characteristic analysis: a tool for the quantitative evaluation of observer performance and imaging systems | |
| Rubin | Lung nodule and cancer detection in computed tomography screening | |
| AU2006317424B2 (en) | Method and system of computer-aided quantitative and qualitative analysis of medical images | |
| JP5475923B2 (en) | Similar case retrieval apparatus and similar case retrieval method | |
| CN101032423B (en) | Realtime interactive data analysis management tool | |
| RU2566462C2 (en) | System and method of computerised diagnostics with multiple modalities | |
| US20120166211A1 (en) | Method and apparatus for aiding imaging diagnosis using medical image, and image diagnosis aiding system for performing the method | |
| CN106415555A (en) | System and method for correlation of pathology reports and radiology reports | |
| JP6215227B2 (en) | Imaging inspection protocol update recommendation section | |
| CN102265308A (en) | System for monitoring medical abnormalities and method of operation thereof | |
| JP2019526869A (en) | CAD system personalization method and means for providing confidence level indicators for CAD system recommendations | |
| Huang et al. | Artificial intelligence aids cardiac image quality assessment for improving precision in strain measurements | |
| Kim et al. | Utility of CT texture analysis in differentiating low-attenuation renal cell carcinoma from cysts: a bi-institutional retrospective study | |
| JP6448588B2 (en) | Medical diagnosis support apparatus, medical diagnosis support system, information processing method, and program | |
| KR101656582B1 (en) | Method and system for detection of thyroid nodules | |
| EP3362925B1 (en) | Systems and methods for generating correct radiological recommendations | |
| CN112842394A (en) | Ultrasonic imaging system, ultrasonic imaging method and storage medium | |
| JP5001002B2 (en) | Image diagnosis support apparatus and method | |
| JP3956234B2 (en) | Medical image processing device | |
| JP6316325B2 (en) | Information processing apparatus, information processing apparatus operating method, and information processing system | |
| JP6827940B2 (en) | Guided structured reporting | |
| Dundas et al. | Artificial Intelligence–based Coronary Stenosis Quantification at Coronary CT Angiography versus Quantitative Coronary Angiography | |
| CN115485784A (en) | Real-time AI for physical biopsy marker detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20160316 Address after: Osaka Japan Patentee after: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT Co.,Ltd. Address before: Osaka Japan Patentee before: Matsushita Electric Industrial Co.,Ltd. |